CVHCMar 13, 2017

Guetzli: Perceptually Guided JPEG Encoder

arXiv:1703.04421v142 citations
Originality Incremental advance
AI Analysis

This addresses the need for more efficient image compression for web and storage applications, though it is incremental as it builds on existing JPEG standards.

Guetzli tackles the problem of JPEG image compression by producing visually indistinguishable images at lower bit-rates, achieving a 29-45% reduction in data size compared to other compressors.

Guetzli is a new JPEG encoder that aims to produce visually indistinguishable images at a lower bit-rate than other common JPEG encoders. It optimizes both the JPEG global quantization tables and the DCT coefficient values in each JPEG block using a closed-loop optimizer. Guetzli uses Butteraugli, our perceptual distance metric, as the source of feedback in its optimization process. We reach a 29-45% reduction in data size for a given perceptual distance, according to Butteraugli, in comparison to other compressors we tried. Guetzli's computation is currently extremely slow, which limits its applicability to compressing static content and serving as a proof- of-concept that we can achieve significant reductions in size by combining advanced psychovisual models with lossy compression techniques.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes